Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2105 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 18.3253. Min Range: -18.3253
Max Act: 18.3253. Min Act: -0.1700
Data Index: 3007003 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.9503. Min Act: -0.1700
Data Index: 6365304 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.8253. Min Act: -0.1700
Data Index: 2055792 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.7003. Min Act: -0.1700
Data Index: 6594437 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.7003. Min Act: -0.1700
Data Index: 8330039 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.7003. Min Act: -0.1700
Data Index: 555914 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.7003. Min Act: -0.1700
Data Index: 4588090 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.5753. Min Act: -0.1700
Data Index: 4087974 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.5753. Min Act: -0.1700
Data Index: 4904465 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.5753. Min Act: -0.1700
Data Index: 4255840 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.5753. Min Act: -0.1700
Data Index: 3476319 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.4503. Min Act: -0.1700
Data Index: 3390196 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.4503. Min Act: -0.1700
Data Index: 1709900 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.4503. Min Act: -0.1700
Data Index: 4810740 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.3253. Min Act: -0.1700
Data Index: 3202401 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.4503. Min Act: -0.1700
Data Index: 5641802 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.4503. Min Act: -0.1700
Data Index: 457989 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.4503. Min Act: -0.1700
Data Index: 2709786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.4503. Min Act: -0.1700
Data Index: 2459586 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.3253. Min Range: -18.3253
Max Act: 17.4503. Min Act: -0.1700
Data Index: 5918817 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19